Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7859. Min Act: -0.1700
Data Index: 2327219 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7702. Min Act: -0.1700
Data Index: 4536195 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7859. Min Act: -0.1700
Data Index: 7049983 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7389. Min Act: -0.1700
Data Index: 3365501 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7546. Min Act: -0.1700
Data Index: 7737948 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7233. Min Act: -0.1700
Data Index: 2555934 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7077. Min Act: -0.1700
Data Index: 4905768 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7233. Min Act: -0.1700
Data Index: 4937270 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 7506848 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 2783907 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 3343665 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7077. Min Act: -0.1700
Data Index: 2787959 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 211150 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6764. Min Act: -0.1700
Data Index: 4469425 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 5848057 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6764. Min Act: -0.1700
Data Index: 3352200 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6607. Min Act: -0.1700
Data Index: 7280594 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6607. Min Act: -0.1700
Data Index: 7945950 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6294. Min Act: -0.1700
Data Index: 5269275 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6138. Min Act: -0.1700
Data Index: 5192322 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19